复杂背景下多姿态人脸图像中的人眼检测

山东大学学报(工学版)

复杂背景下多姿态人脸图像中的人眼检测

董文会_1, 曲培树_2,吴晓娟_1, 徐祗军_1,

1. 山东大学信息科学与工程学院，山东济南250100；2. 德州学院物理系，山东德州253023

收稿日期:2005-03-06 修回日期:1900-01-01 出版日期:2006-06-24 发布日期:2006-06-24
通讯作者: 董文会_1,

Eye detection for multipose face image in complex background

DONG Wenhui_1,QU Peishu_2,WU Xiaojuan_1,XU Zhijun_1,

1. School of Information Science and Engineering,Shandong University，Jinan 250100，China;2. Physics Department,Dezhou University,Dezhou 253023,China

Received:2005-03-06 Revised:1900-01-01 Online:2006-06-24 Published:2006-06-24
Contact: DONG Wenhui_1,

摘要/Abstract

摘要： 研究了复杂背景下多姿态人脸图像中的人眼检测方法.首先，将得到的图像映射到YCbCr空间，利用肤色在YCbCr颜色空间的分布特性建立肤色模型，分割出肤色并得到人脸的区域；再次，利用人眼的分布特点及自身特性预先设定一系列的规则，通过规则得到可能的人眼区域；最后，设计了人眼模板分布模型，并利用该模型对人眼位置进行最后的确认.实验表明，该方法具有较高的检测速度和检测正确率.

关键词: YCbCr空间, 肤色分割, 人眼检测

Abstract: Eye detection method for multipose face image in complex background is studied. Firstly, we project the image to YCbCr space and get skin and face region by the skin model based on the distribution of the skin; secondly, the possible eye regions can be found according to the rules formulated by the eye distribution and its characteristics; lastly, the eye position is confirmed by eye templates distribution model. Experiment results show that the method is efficient and precise.

Key words: skin color segmentation, eye detection , YCbCr color space

董文会,曲培树,吴晓娟,徐祗军 . 复杂背景下多姿态人脸图像中的人眼检测[J]. 山东大学学报(工学版), 2006, 36(3): 18-21 .

DONG Wenhui,QU Peishu,WU Xiaojuan,XU Zhijun, . Eye detection for multipose face image in complex background[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(3): 18-21 .

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed